Papers
3
Total Citations
7
H-Index
2
About
Lingxiang Hu is a robotics researcher focused on enabling real-time visual perception for autonomous systems, particularly in robotic navigation and human-robot interaction. Their work centers on developing efficient deep learning models that balance accuracy with the computational constraints of embedded robotic platforms. Hu’s major contributions include a hybrid approach to real-time robotic visual navigation that integrates object detection with scene segmentation, achieving practical performance for autonomous operation. They also developed an optimized YOLO-based model for real-time hand keypoint detection, addressing the challenge of gesture recognition on resource-limited devices. Additionally, Hu conducted a comprehensive study of deep learning visual odometry for mobile robot localization in indoor environments, combining multi-sensor fusion to improve positioning accuracy. Though early in their career, Hu’s recent publications (2024) have already garnered citations, reflecting growing interest in their pragmatic, application-driven methodologies. Their work stands out for tackling the critical trade-off between high accuracy and real-time efficiency, making it directly relevant to students and researchers working on deployable robotic vision systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3